arXiv subjects

Xinwei Qiang

Publications and source records attributed to Xinwei Qiang.

8 recordsLinked to original sources

arXiv2026

Zepp: Accelerating Distributed MoE Serving under Relaxed Balance Constraints

As Mixture-of-Experts (MoE) models continue to scale, serving them increasingly relies on expert parallelism (EP) across a growing number of devices. Yet skewed expert workloads create imbalance across computation, communication, and memory, making load balancing a central optimization objective in distributed MoE serving. We observe that balance is not free: operations introduced to balance one dimension can themselves be expensive or imbalanced. This motivates us to rethink balance as a constraint rather than an optimization objective. We present Zepp, which directly optimizes the bottleneck communication in distributed MoE serving subject to simplified balance constraints on physical resources, i.e., GPUs and NICs. Zepp progressively optimizes inter-node communication across placement, routing, and execution. It first places expert replicas to reduce token communication under GPU constraints, then reshapes communication flows through split and merge primitives under NIC constraints, and finally partitions and schedules ex- pert computation to overlap the resulting communication. To adapt to dynamic workloads, Zepp jointly coordinates computation, token communication, and expert-weight movement at each iteration. Together, these designs allow Zepp to pursue the most efficient execution rather than a single-dimension balanced one. We implement Zepp and evaluate it against 7 state-of-the-art MoE serving systems, achieving up to 6.68$\times$ MoE layer speedup and a geometric mean speedup of 1.86$\times$ over the fastest competing baseline.

cs.DC↗

arXiv2026

RR-Evict: Fine-Grained Prefix Cache Eviction beyond LRU for Agentic LLM Serving

LLM-based agents execute long-horizon tasks through repeated model calls interleaved with tool execution and user interaction. As each call extends the history accumulated in previous turns, prefix caching avoids repeated prefill of the agent's entire context. However, the aggregate cache footprint grows with context length and concurrency, forcing serving systems to reclaim cached KV tensors. We identify recency synchronization: accesses to an agent's cached history refresh its cache nodes together, causing least recently used (LRU) eviction to concentrate on a few agents' private histories. When a fully evicted agent returns, it must recompute nearly its entire accumulated context, producing a large time-to-first-token (TTFT) outlier even if most other requests retain substantial cache reuse. We present RR-EVICT, a fine-grained prefix-cache eviction strategy that distributes reclamation across idle agent trajectories. RR-EVICT visits agents in round-robin order and evicts a tail chunk from each, preserving reusable prefixes for more agents when capacity remains for idle state. Returning agents can reuse these partial histories and recompute smaller missing suffixes. The policy requires no prediction of future arrivals or tool latency. We implement RR-EVICT in SGLang and evaluate conversational and coding-agent workloads under colocated and prefill-decode-disaggregated serving. Compared with LRU, RR-EVICT reduces P99 TTFT by up to 75.4% and P99 uncached prompt tokens by up to 65.7%.

cs.DC↗

arXiv2026

Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Measurements across four domains and four open-weight targets, plus floor estimates on a frontier API target, yield three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for $43$--$64\%$ of DFlash rejection and $85$--$92\%$ of DSpark's oracle-conditioned rejection. Guided by this separation of short-range conditioning from proposal quality, we replace a context-independent predecessor correction with a prefix-attention head that reads committed context conditional on the predecessor. With supporting backbone components, the resulting Qwen3-4B drafter improves mean serving accepted length by $3.93\%$ over the released DSpark checkpoint across nine tasks, without increasing the conditioning order. Code and data: https://github.com/tie-pilot-qxw/specfloor; drafter checkpoints: https://huggingface.co/TIE-Pilot/dspark-attnconv-block7-qwen3-4b.

cs.LG↗

arXiv2026

AgentReplay: Token-Wise Trace Replay Is Essential for Fair Serving System Performance Benchmarking

LLM-based agents execute multi-turn workflows with interleaved model inference and tool calls, making efficient serving increasingly important. However, evaluating serving optimizations is challenging because identical tasks can produce different execution trajectories. Changes in generated tokens can alter subsequent prompts, tool calls, and reasoning turns, making it difficult to distinguish system improvements from workload variation. Greedy decoding does not guarantee identical outputs, while replaying only sequence lengths loses token information that affects prefix caching and mixture-of-experts (MoE) routing. To address these problems, we propose AgentReplay, a configurable trace record-and-replay framework for agent serving. AgentReplay records input/output tokens, expert selections, request dependencies, and tool durations. During replay, it forces the recorded output tokens while performing normal autoregressive computation, with optional controls for MoE expert selection and tool delays. This allows different systems to execute the same recorded workload while retaining their own batching, scheduling, and parallelization decisions. We further separate trajectory generation from performance evaluation, enabling compatible smaller models to replay long-horizon traces collected with more capable models. Our experiments show that token-wise replay in AgentReplay effectively eliminates workload variation that greedy decoding and length-wise replay cannot avoid, enabling fairer performance comparisons across serving configurations.

cs.DC↗

arXiv2026

Argus: Orchestrating Cross-Layer GPU Performance Measurements around Semantic Regions

GPU developers and automated optimizers need performance evidence for semantic code regions--such as neural-network operator implementations and pipeline stages--but this evidence is fragmented across profiling tools. Answering a region-level question can require manually constructing probes and program variants, isolating interfering measurements, and mapping evidence to regions and execution contexts. We present Argus, a region-centric measurement planner and runtime that automates this workflow. Clients identify regions with boundary markers and select signals and execution scopes. Argus preserves region identity across compilation, execution, and measurement variants, constructs interference-aware multi-run plans, and orchestrates transformations and profiling across backends. It joins compiler-, hardware-, and system-level evidence using region identity and dynamic execution context, producing reports that record measurement origins and attribution ambiguity. We evaluate Argus across agentic kernel optimization, persistent megakernel optimization, and cross-level PGO. Across 44 persistent-GEMM and attention configurations, Argus improves 39/44 cases and raises AlphaEvolve's geometric-mean speedup from 5.4% to 8.9%. On a persistent TinyLlama-1.1B decode megakernel, an optimization agent reaches 1.65 ms/token with Argus versus 4.92 ms/token without it, producing a kernel $2.1\times$ faster than PyTorch with CUDA Graphs. Finally, Argus-guided cross-level PGO improves compute--communication overlap, increasing throughput by 7% on average across five multi-GPU settings.

cs.DC↗

arXiv2026

GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving

Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each request a fixed parallel configuration throughout its lifetime. However, DiT workloads exhibit substantial heterogeneity across requests, execution stages, and system conditions, making static parallelism inefficient and often leading to poor GPU utilization and degraded service quality. This paper argues that DiT serving should treat GPU parallelism as a first-class schedulable resource. We present GF-DiT, a policy-programmable runtime for elastic DiT serving that dynamically adapts the parallelism of running requests according to workload demands and service objectives. GF-DiT introduces an asynchronous execution abstraction that decomposes requests into independently schedulable trajectory tasks and enables online GPU reallocation. To make elastic parallelism practical, GF-DiT further proposes group-free collectives, a lightweight communication abstraction that supports low-overhead online formation and reconfiguration of arbitrary execution groups. We implement GF-DiT in vLLM-Omni and evaluate it on representative image and video diffusion workloads. Compared with fixed-pipeline execution with static parallelism, GF-DiT improves throughput by up to 6.01$\times$, reduces mean latency by up to 95%, lowers SLO violation rates by up to 90%, and reduces communication-group setup overhead from 778 ms to approximately 60 $μ$s. Our code is available at https://github.com/SJTU-Liquid/GF-DiT.

cs.DC↗

arXiv2026

Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap

Communication has become a first-order bottleneck in large-scale GPU workloads, and existing distributed compilers address it mainly by overlapping whole compute and communication kernels at the stream level. This coarse granularity incurs extra kernel launches, forces device-wide synchronizations at kernel boundaries, and leaves substantial slack when the slowest tile or kernel stretches the communication tail. We present Syncopate, a compiler and runtime that enables automatic fine-grained overlap inside a single fused kernel. Syncopate introduces a communication chunk abstraction that decouples communication granularity from kernel structure and backend mechanisms, allowing chunk-level plans to be ported from existing distributed compilers, written directly by users, or instantiated from reusable templates. Given a local Triton kernel and a chunk schedule, Syncopate performs transformations to align computation with chunk availability. Implemented as a source-to-source compiler on Triton, Syncopate delivers an average end-to-end speedup of 1.3$\times$ and up to 4.7$\times$ on multi-GPU workloads. Our code is open-sourced at https://github.com/tie-pilot-qxw/syncopate.

cs.DC↗

arXiv2026

DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training

Determinism is indispensable for reproducibility in large language model (LLM) training, yet it often exacts a steep performance cost. In widely used attention implementations such as FlashAttention-3, the deterministic backward pass can incur up to a 37.9% throughput reduction relative to its non-deterministic counterpart, primarily because gradient accumulation operations must be serialized to guarantee numerical consistency. This performance loss stems from suboptimal scheduling of compute and gradient-reduction phases, leading to significant hardware underutilization. To address this challenge, we formulate the backward pass of deterministic attention as a scheduling problem on a Directed Acyclic Graph (DAG) and derive schedules that minimize the critical path length. Building on this formulation, we present DASH (Deterministic Attention Scheduling for High-Throughput), which encapsulates two complementary scheduling strategies: (i) Descending Q-Tile Iteration, a reversed query-block traversal that shrinks pipeline stalls in causal attention, and (ii) Shift Scheduling, a theoretically optimal schedule within our DAG model that reduces pipeline stalls for both full and causal masks. Our empirical evaluations on NVIDIA H800 GPUs demonstrate that DASH narrows the performance gap of deterministic attention. The proposed strategies improve the throughput of the attention backward pass by up to 1.28$\times$ compared to the baseline, significantly advancing the efficiency of reproducible LLM training. Our code is open-sourced at https://github.com/SJTU-Liquid/deterministic-FA3.

cs.LG↗